Vulnerable Agent Identification in Large-Scale Multi-Agent Reinforcement Learning

• URL: http://arxiv.org/abs/2509.15103v2
• Date: Fri, 19 Sep 2025 08:02:22 GMT
• Title: Vulnerable Agent Identification in Large-Scale Multi-Agent Reinforcement Learning
• Authors: Simin Li, Zheng Yuwei, Zihao Mao, Linhao Wang, Ruixiao Xu, Chengdong Ma, Xin Yu, Yuqing Ma, Qi Dou, Xin Wang, Jie Luo, Bo An, Yaodong Yang, Weifeng Lv, Xianglong Liu,
• Abstract summary: Partial agent failure becomes inevitable when systems scale up, making it crucial to identify the subset of agents whose compromise would most severely degrade overall performance.<n>In this paper, we study this Vulnerable Agent Identification (VAI) problem in large-scale multi-agent reinforcement learning (MARL)<n> Experiments show our method effectively identifies more vulnerable agents in large-scale MARL and the rule-based system, fooling system into worse failures, and learning a value function that reveals the vulnerability of each agent.
• Score: 49.31650627835956
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Partial agent failure becomes inevitable when systems scale up, making it crucial to identify the subset of agents whose compromise would most severely degrade overall performance. In this paper, we study this Vulnerable Agent Identification (VAI) problem in large-scale multi-agent reinforcement learning (MARL). We frame VAI as a Hierarchical Adversarial Decentralized Mean Field Control (HAD-MFC), where the upper level involves an NP-hard combinatorial task of selecting the most vulnerable agents, and the lower level learns worst-case adversarial policies for these agents using mean-field MARL. The two problems are coupled together, making HAD-MFC difficult to solve. To solve this, we first decouple the hierarchical process by Fenchel-Rockafellar transform, resulting a regularized mean-field Bellman operator for upper level that enables independent learning at each level, thus reducing computational complexity. We then reformulate the upper-level combinatorial problem as a MDP with dense rewards from our regularized mean-field Bellman operator, enabling us to sequentially identify the most vulnerable agents by greedy and RL algorithms. This decomposition provably preserves the optimal solution of the original HAD-MFC. Experiments show our method effectively identifies more vulnerable agents in large-scale MARL and the rule-based system, fooling system into worse failures, and learns a value function that reveals the vulnerability of each agent.

Related papers

• Explainable and Fine-Grained Safeguarding of LLM Multi-Agent Systems via Bi-Level Graph Anomaly Detection [76.91230292971115]
  Large language model (LLM)-based multi-agent systems (MAS) have shown strong capabilities in solving complex tasks.<n>XG-Guard is an explainable and fine-grained safeguarding framework for detecting malicious agents in MAS.
  arXiv  Detail & Related papers  (2025-12-21T13:46:36Z)
• Bilevel Optimization for Covert Memory Tampering in Heterogeneous Multi-Agent Architectures (XAMT) [0.0]
  Multi-Agent Systems (MAS) are inherently heterogeneous, integrating conventional Multi-Agent Reinforcement Learning (MARL) with emerging Large Language Model (LLM) agent architectures.<n>A critical shared vulnerability is reliance on centralized memory components: the shared Experience Replay (ER) buffer in MARL and the external Knowledge Base (K) in RAG agents.<n>This paper proposes XAMT (Bilevel Optimization for Covert Memory Tampering in Heterogeneous Multi-Agent Architectures), a novel framework that formalizes attack generation as a bilevel optimization problem.
  arXiv  Detail & Related papers  (2025-12-15T23:04:48Z)
• AdvEvo-MARL: Shaping Internalized Safety through Adversarial Co-Evolution in Multi-Agent Reinforcement Learning [78.5751183537704]
  AdvEvo-MARL is a co-evolutionary multi-agent reinforcement learning framework that internalizes safety into task agents.<n>Rather than relying on external guards, AdvEvo-MARL jointly optimize attackers and defenders.
  arXiv  Detail & Related papers  (2025-10-02T02:06:30Z)
• Agent-Oriented Planning in Multi-Agent Systems [54.429028104022066]
  We propose AOP, a novel framework for agent-oriented planning in multi-agent systems.<n>In this study, we identify three critical design principles of agent-oriented planning, including solvability, completeness, and non-redundancy.<n> Extensive experiments demonstrate the advancement of AOP in solving real-world problems compared to both single-agent systems and existing planning strategies for multi-agent systems.
  arXiv  Detail & Related papers  (2024-10-03T04:07:51Z)
• Byzantine-Resilient Decentralized Multi-Armed Bandits [23.34196562182705]
  We develop an algorithm that fuses an information mixing step among agents with a truncation of inconsistent and extreme values.<n>This framework can be used to model attackers in computer networks, instigators of offensive content into recommender systems, or manipulators of financial markets.
  arXiv  Detail & Related papers  (2023-10-11T09:09:50Z)
• On the Complexity of Multi-Agent Decision Making: From Learning in Games to Partial Monitoring [105.13668993076801]
  A central problem in the theory of multi-agent reinforcement learning (MARL) is to understand what structural conditions and algorithmic principles lead to sample-efficient learning guarantees. We study this question in a general framework for interactive decision making with multiple agents. We show that characterizing the statistical complexity for multi-agent decision making is equivalent to characterizing the statistical complexity of single-agent decision making.
  arXiv  Detail & Related papers  (2023-05-01T06:46:22Z)
• The challenge of redundancy on multi-agent value factorisation [12.63182277116319]
  In the field of cooperative multi-agent reinforcement learning (MARL), the standard paradigm is the use of centralised training and decentralised execution. We propose leveraging layerwise relevance propagation (LRP) to instead separate the learning of the joint value function and generation of local reward signals. We find that although the performance of both baselines VDN and Qmix degrades with the number of redundant agents, RDN is unaffected.
  arXiv  Detail & Related papers  (2023-03-28T20:41:12Z)
• Relative Distributed Formation and Obstacle Avoidance with Multi-agent Reinforcement Learning [20.401609420707867]
  We propose a distributed formation and obstacle avoidance method based on multi-agent reinforcement learning (MARL) Our method achieves better performance regarding formation error, formation convergence rate and on-par success rate of obstacle avoidance compared with baselines.
  arXiv  Detail & Related papers  (2021-11-14T13:02:45Z)
• HAVEN: Hierarchical Cooperative Multi-Agent Reinforcement Learning with Dual Coordination Mechanism [17.993973801986677]
  Multi-agent reinforcement learning often suffers from the exponentially larger action space caused by a large number of agents. We propose a novel value decomposition framework HAVEN based on hierarchical reinforcement learning for the fully cooperative multi-agent problems.
  arXiv  Detail & Related papers  (2021-10-14T10:43:47Z)
• Permutation Invariant Policy Optimization for Mean-Field Multi-Agent Reinforcement Learning: A Principled Approach [128.62787284435007]
  We propose the mean-field proximal policy optimization (MF-PPO) algorithm, at the core of which is a permutation-invariant actor-critic neural architecture. We prove that MF-PPO attains the globally optimal policy at a sublinear rate of convergence. In particular, we show that the inductive bias introduced by the permutation-invariant neural architecture enables MF-PPO to outperform existing competitors.
  arXiv  Detail & Related papers  (2021-05-18T04:35:41Z)
• F2A2: Flexible Fully-decentralized Approximate Actor-critic for Cooperative Multi-agent Reinforcement Learning [110.35516334788687]
  Decentralized multi-agent reinforcement learning algorithms are sometimes unpractical in complicated applications. We propose a flexible fully decentralized actor-critic MARL framework, which can handle large-scale general cooperative multi-agent setting. Our framework can achieve scalability and stability for large-scale environment and reduce information transmission.
  arXiv  Detail & Related papers  (2020-04-17T14:56:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.